proofhub-mcp
A zero-dependency MCP server for ProofHub that provides tools to manage tasks, projects, and comments, and includes BMAD sharding to turn tickets into self-contained stories.
README
proofhub-mcp
ProofHub for Claude Code — a zero-dependency MCP server (and a CLI) over the ProofHub v3 API, with a BMAD ticket-to-story sharder. Bring your own key; nothing about your account ships in the package.
- MCP server (primary): native tools to list / create / comment / complete tasks, and to shard a ticket into a self-contained BMAD story — so a coding agent can act without re-opening the ticket.
- CLI (bundled): the same operations from your terminal, CI, or cron.
Install as a Claude Code plugin
/plugin marketplace add yashmody/proofhub-mcp
/plugin install proofhub@proofhub-mcp
Then provide your key (bring-your-own-key) by exporting these before launching Claude Code:
export PROOFHUB_ACCOUNT="yourteam" # "yourteam" or "yourteam.proofhub.com"
export PROOFHUB_API_KEY="your-api-key" # ProofHub → profile → API access
claude
Run /mcp to confirm the proofhub server is connected. Tools then appear as
mcp__proofhub__list_tasks, mcp__proofhub__create_task, mcp__proofhub__shard_to_story, etc.
MCP tools
| Tool | Does |
|---|---|
proofhub_list_projects |
list projects |
proofhub_list_todolists |
list task lists in a project |
proofhub_list_tasks |
list tasks in a todolist |
proofhub_get_task |
full JSON for one task |
proofhub_create_task |
create a task |
proofhub_comment |
comment on a task |
proofhub_complete |
mark a task complete |
proofhub_shard_to_story |
BMAD: shard a ticket into a self-contained story file |
BMAD sharding
proofhub_shard_to_story turns a ProofHub ticket into a story with Context / Acceptance
Criteria / Dev Notes / Tasks-Subtasks and a suggested owner role + model tier — BMAD's core
move of embedding full context so the dev agent isn't guessing. See templates/story.md.
CLI (bundled)
export PROOFHUB_ACCOUNT=... PROOFHUB_API_KEY=...
npx -p proofhub-mcp proofhub projects # or, installed: proofhub projects
proofhub tasks <projectId> <todolistId>
proofhub comment <projectId> <todolistId> <ticket> --body "..."
Notes
- Auth header is
X-API-KEY(not Bearer); aUser-Agentis set automatically. The client throttles to ~25 req/10s and honoursRetry-After. - ProofHub returns some errors as HTTP 200 with a
{code,message}envelope — the client surfaces those as errors. Mutations resolve the internal task id from the ticket number automatically.
npm test # no-network self-test
MIT © Yash Mody
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.